Method and system for real time filtering of inappropriate content from plurality of video segments

Abstract

The present disclosure provides a computer-implemented method and system for real-time filtering of an inappropriate content from a plurality of video segments. The method includes a first step of receiving multimedia content. In addition, the method includes another step of segmenting the multimedia content in real-time. Further, the method includes yet another step of identifying the inappropriate content in real-time. Furthermore, the method includes yet another step of filtering of the plurality of video segments in real-time. Moreover, the method includes yet another step of displaying an appropriate video content in real-time.

What is claimed: 
     
         1 . A computer-implemented method for real time filtering of an inappropriate content from a plurality of video segments, the method comprising:
 receiving, at a video filtration system with a processor, one or more multimedia content, wherein the one or more multimedia content is received from one or more input devices;   segmenting, at the video filtration system with the processor, the one or more multimedia content in real-time, wherein the one or more multimedia content is segmented into the plurality of video segments, wherein the one or more multimedia content is segmented into the plurality of video segments based on one or more parameters, wherein the plurality of video segments is ranked based on the one or more parameters;   identifying, at the video filtration system with the processor, an inappropriate content in real-time, wherein the inappropriate content is identified from the plurality of video segments, wherein the inappropriate content is identified using machine learning algorithms;   filtering, at the video filtration system with the processor, the inappropriate content in real-time, wherein the inappropriate content is filtered out using a detection model, wherein the detection model filters the inappropriate content based on one or more pre-defined factors, wherein the filtering of the inappropriate content from the plurality of video segments facilitates generation of an appropriate video content; and   displaying, at the video filtration system with the processor, the appropriate video content in real-time, wherein the appropriate video content is displayed on one or more multimedia channels, wherein the appropriate video content is displayed based on one or more requirements of the one or more multimedia channels.   
     
     
         2 . The computer-implemented method as recited in  claim 1 , wherein the one or more input devices comprising at least one of keyboard, joystick, mouse and digital camera. 
     
     
         3 . The computer-implemented method as recited in  claim 1 , wherein the one or more multimedia content comprising at least one of text, audio, video, animation and graphics interface format (GIF). 
     
     
         4 . The computer-implemented method as recited in  claim 1 , wherein the one or more parameters comprising an audio continuity, a video continuity and an intersection of the audio continuity and the video continuity. 
     
     
         5 . The computer-implemented method as recited in  claim 1 , wherein the inappropriate content comprising nude video content, nude images, inappropriate audio content, violent video content, religiously disrespectful content, political influential content, cultural norms and gender discriminatory content. 
     
     
         6 . The computer-implemented method as recited in  claim 1 , wherein the one or more pre-defined factors comprising at least one of geographical location, age and community. 
     
     
         7 . The computer-implemented method as recited in  claim 1 , wherein the machine learning algorithms comprising at least one of linear regression, logistic regression, random forest, decision tree, and K-nearest neighbor. 
     
     
         8 . The computer-implemented method as recited in  claim 1 , further comprising adaptive-learning of the detection model, at the video filtration system with the processor, wherein the detection model adaptively learns to filter-out the inappropriate content from the plurality of video segments based on training dataset. 
     
     
         9 . The computer-implemented method as recited in  claim 1 , wherein the one or more requirements of the one or more multimedia channels comprising at least one of an orientation of the appropriate content, an aspect ratio of the appropriate content and a duration of the appropriate content. 
     
     
         10 . The computer-implemented method as recited in  claim 1 , further comprising sub-filtering the plurality of video segments, at the video filtration system with the processor, wherein the sub-filtering of the plurality of video segments is effectuated to target a plurality of users at particular geographical location, wherein the sub-filtering is performed based on presence of naked-skin in the plurality of video segments. 
     
     
         11 . A computer system comprising:
 one or more processors; and   a memory coupled to the one or more processors, the memory for storing instructions which, when executed by the one or more processors, cause the one or more processors to perform a method for real time filtering of an inappropriate content from a plurality of video segments, the method comprising:
 receiving, at a video filtration system, one or more multimedia content, wherein the one or more multimedia content is received from one or more input devices; 
 segmenting, at the video filtration system, the one or more multimedia content in real-time, wherein the one or more multimedia content is segmented into the plurality of video segments, wherein the one or more multimedia content is segmented into the plurality of video segments based on one or more parameters, wherein the plurality of video segments is ranked based on the one or more parameters; 
 identifying, at the video filtration system, an inappropriate content in real-time, wherein the inappropriate content is identified from the plurality of video segments, wherein the inappropriate content is identified using machine learning algorithms; 
 filtering, at the video filtration system, the inappropriate content in real-time, wherein the inappropriate content is filtered out using a detection model, wherein the detection model filters the inappropriate content based on one or more pre-defined factors, wherein the filtering of the inappropriate content from the plurality of video segments facilitates generation of an appropriate video content; and 
 displaying, at the video filtration system, the appropriate video content in real-time, wherein the appropriate video content is displayed on one or more multimedia channels, wherein the appropriate video content is displayed based on one or more requirements of the one or more multimedia channels. 
   
     
     
         12 . The computer system as recited in  claim 11 , wherein the one or more input devices comprising at least one of keyboard, joystick, mouse and digital camera. 
     
     
         13 . The computer system as recited in  claim 11 , wherein the one or more multimedia content comprising at least one of text, audio, video, animation and graphics interface format (GIF). 
     
     
         14 . The computer system as recited in  claim 11 , wherein the one or more parameters comprising an audio continuity, a video continuity and an intersection of the audio continuity and the video continuity. 
     
     
         15 . The computer system as recited in  claim 11 , wherein the inappropriate content comprising nude video content, nude images, inappropriate audio content, violent video content, religiously disrespectful content, political influential content, cultural norms and gender discriminatory content. 
     
     
         16 . The computer system as recited in  claim 11 , wherein the one or more pre-defined factors comprising at least one of geographical location, age and community. 
     
     
         17 . The computer system as recited in  claim 11 , wherein the machine learning algorithms comprising at least one of linear regression, logistic regression, random forest, decision tree, and K-nearest neighbor. 
     
     
         18 . The computer system as recited in  claim 11 , further comprising adaptive-learning of the detection model, at the video filtration system, wherein the detection model adaptively learns to filter-out the inappropriate content from the plurality of video segments based on training dataset. 
     
     
         19 . A non-transitory computer-readable storage medium encoding computer executable instructions that, when executed by at least one processor, performs a method for real time filtering of an inappropriate content from a plurality of video segments, the method comprising:
 receiving, at a computing device, one or more multimedia content, wherein the one or more multimedia content is received from one or more input devices;   segmenting, at the computing device, the one or more multimedia content in real-time, wherein the one or more multimedia content is segmented into the plurality of video segments, wherein the one or more multimedia content is segmented into the plurality of video segments based on one or more parameters, wherein the plurality of video segments is ranked based on the one or more parameters;   identifying, at the computing device, an inappropriate content in real-time, wherein the inappropriate content is identified from the plurality of video segments, wherein the inappropriate content is identified using machine learning algorithms;   filtering, at the computing device, the inappropriate content in real-time, wherein the inappropriate content is filtered out using a detection model, wherein the detection model filters the inappropriate content based on one or more pre-defined factors, wherein the filtering of the inappropriate content from the plurality of video segments facilitates generation of an appropriate video content; and   displaying, at the computing device, the appropriate video content in real-time, wherein the appropriate video content is displayed on one or more multimedia channels, wherein the appropriate video content is displayed based on one or more requirements of the one or more multimedia channels.   
     
     
         20 . The non-transitory computer-readable storage medium as recited in  claim 19 , further comprising adaptive-learning of the detection model, at the computing device, wherein the detection model adaptively learns to filter-out the inappropriate content from the plurality of video segments based on training dataset.